一种基于遗传算法的机器人补偿学习控制方法

机器人建模的不精确性以及一些扰动的存在给机器人控制增加了相当大的难度。针时这一问题，本文以PUMA560机器人为被控对象，给出了一种PUMA560机器人动力学模型的简化形式，采用PD控制的计算力矩法，得到了机器人的闭环动态误差方程，在此基础上设计了机器人的控制器结构，提出了一种新的基于遗传算法(Genetic algorithm，GA)的机器人补偿学习控制方法。将GA与计算力矩法相结合，利用进化学习来消除机器人中不确定因素的影响，实现时机器人轨迹跟踪的良好控制。最后给出了这种控制的仿真结果，验证了该方法的有效性。

Compensating Learning Control for Robot Using Genetic Algorithm

The uncertainties and disturbances in the robot dynamic system make the robot control much more difficult. Aiming at this problem, an explicit dynamic model for PUMA 560 robot is given. The closed-loop dynamic error equation considering uncertainties for the robot is derived by using the computed torque method with PD type. A new learning control method using real coded genetic algorithm (GA) is presented to control the PUMA560 robot and its controller structure is designed. In terms of the operations such as arithmetical crossover, non-uniform mutation and normalized geometric distribution in the GA, a real coded compensating learning control item is added to the error equation to approach the uncertainties by evolutionary learning. Then, the computed torque method and the GA learning control are combined to realize the perfect trajectory tracking. Simulation results show the efficiency of the control method.